知搜-全球专利检索

  1. 登录
  2. 注册

搜索结果

4 条记录 (耗时 0.016 秒)

    Intention-driven reinforcement learning-based path planning method
    2.
    发明授权
    Intention-driven reinforcement learning-based path planning method 有权

    公开(公告)号：US12124282B2

    公开(公告)日：2024-10-22

    申请号：US17923114

    申请日：2021-12-13

    申请人： SOUTHEAST UNIVERSITY

    发明人： Hua Zhang ,  Na Su ,  Junbo Wang

    IPC分类号： G05D1/644 ,  B63B79/40 ,  G05D101/15 ,  G05D109/30

    CPC分类号： G05D1/644 ,  B63B79/40 ,  G05D2101/15 ,  G05D2109/30

    摘要： The present invention discloses an intention-driven reinforcement learning-based path planning method, including the following steps: 1: acquiring, by a data collector, a state of a monitoring network; 2: selecting a steering angle of the data collector according to positions of surrounding obstacles, sensor nodes, and the data collector; 3: selecting a speed of the data collector, a target node, and a next target node as an action of the data collector according to an ε greedy policy; 4: determining, by the data collector, the next time slot according to the selected steering angle and speed; 5: obtaining rewards and penalties according to intentions of the data collector and the sensor nodes, and updating a Q value; 6: repeating step 1 to step 5 until a termination state or a convergence condition is satisfied; and 7: selecting, by the data collector, an action in each time slot having the maximum Q value as a planning result, and generating an optimal path. The method provided in the present invention can complete the data collection path planning with a higher probability of success and performance closer to the intention.

    Offloading method, of satellite-to-ground edge computing task, assisted by satellite and high-altitude platform
    3.
    发明授权
    Offloading method, of satellite-to-ground edge computing task, assisted by satellite and high-altitude platform 有权

    公开(公告)号：US11916997B2

    公开(公告)日：2024-02-27

    申请号：US17628571

    申请日：2021-04-25

    申请人： SOUTHEAST UNIVERSITY

    发明人： Junbo Wang ,  Changfeng Ding ,  Hua Zhang

    IPC分类号： H04L67/10 ,  H04B7/0456 ,  H04B7/185

    CPC分类号： H04L67/10 ,  H04B7/0456 ,  H04B7/18504 ,  H04B7/18513

    摘要： An offloading method, of a satellite-to-ground edge computing task, assisted by a satellite and a high-altitude platform can offload a computing task of a ground user equipment (GUE) to a low earth-orbit satellite (LEO SAT), to meet a computing requirement of the GUE and to reduce latency and energy consumption. The method includes four main steps: 1. The GUE selects an associated high-altitude platform. 2. The GUE uses multi-input and multi-output (MIMO) transmission to offload the computing task to the high-altitude platform. 3. The high-altitude platform may also use the MIMO transmission to offload the computing task of the GUE to the LEO SAT. 4. The high-altitude platform and the LEO SAT cooperate to process the computing task of GUE, and reasonably allocate a computing resource to reduce energy consumption; and in MIMO edge computing, the GUE or the high-altitude platform uses the same time-domain and frequency-domain resource.